RedHat · IBM Cloud gx3 instance 1xL40S-PCIE-48GB ,vLLM
Llama-3.1-8B (MLPerf reference) · llama3.1-8b · Offline · run 01a00b49-9111…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported1,642.22 tokens_s
Llama-3.1-8B (MLPerf reference) · llama3.1-8b · Offline · offline · 1× NVIDIA L40S · mlperf_closed_99 · observed 2025-09-04
Identity
modelLlama-3.1-8B (MLPerf reference)
stackvLLM 0.10.0, RHEL 9.6
workloadllama3.1-8b · Offline
topology1× NVIDIA L40S
harnessmlperf_loadgen v5.1
quality policymlperf_closed_99
comparison keysha256:c7213e469d0f28b5…
sha256:dcd2282cd2ea9dd1619f950…
Launch configuration
dtypefp8
notesIBM Cloud gx3 instance with 2xL40S-PCIE-48G (1 GPU used). IBM Cloud instance gx3-48x240x2l40s ( 1 GPU used), RHEL 9.6, vllm 0.10.0
systemIBM Cloud gx3 instance 1xL40S-PCIE-48GB ,vLLM
softwarevLLM 0.10.0, RHEL 9.6
availabilityavailable
Workload
namellama3.1-8b · Offline
streamingno
load generationoffline
Canonical manifest
Show manifestHide manifest
{
"kind": "ServingRun",
"spec": {
"status": "valid",
"harness": {
"name": "mlperf_loadgen",
"version": "v5.1"
},
"topology": {
"nodeCount": 1,
"acceleratorModel": "NVIDIA L40S",
"acceleratorVendor": "nvidia",
"acceleratorsPerNode": 1
},
"observedAt": "2025-09-04T19:30:14Z",
"modelDigest": "sha256:dafdb8bb411a12b698d36856eed69f16242fb467999fb68680ca09a5601b6bd4",
"measurements": [
{
"unit": "tokens_s",
"value": 1642.22,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 1642.22
},
"category": "datacenter",
"division": "closed",
"scenario": "offline",
"benchmark": "llama3.1-8b",
"externalId": "v5.1/5.1-0082"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:a49a37592d011507287e85cda6488466913158a2cd8c7ecb16cf07f92327bf15",
"configurationDigest": "sha256:aa24d922465039fdb9036fce53418d96ff8f6a18dd6b596b6991f791033c635d"
},
"metadata": {
"name": "mlperf-v5-1-5-1-0082",
"title": "RedHat · llama3.1-8b · Offline",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/inference_results_v5.1/tree/main/closed/RedHat/results/IBM_Cloud_gx3-48x240x2l40s_vLLM"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v5.1/5.1-0082 · shown unmodified as publishedAll serving results →JSON